3038 search results - page 329 / 608 » High-Speed Function Approximation |
156
click to vote
NIPS
2001
15 years 8 months ago
2001
Policy gradient methods for reinforcement learning avoid some of the undesirable properties of the value function approaches, such as policy degradation (Baxter and Bartlett, 2001...
166
click to vote
BROADBAND
1998
15 years 8 months ago
1998
ATM switches have to provide traffic management functions to meet the QoS requirements of different service categories. Among the traffic management functions we will focus on con...
224
click to vote
NIPS
1997
15 years 8 months ago
1997
There are many applications in which it is desirable to order rather than classify instances. Here we consider the problem of learning how to order, given feedback in the form of ...
162
click to vote
COR
2006
15 years 6 months ago
2006
This paper presents an extension of the capacitated facility location problem (CFLP), in which the general setup cost functions and multiple facilities in one site are considered....
222
click to vote
DSP
2006
15 years 6 months ago
2006
In linear image restoration, the point spread function of the degrading system is assumed known even though this information is usually not available in real applications. As a re...